research-grants

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/research-grants/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured with excellent progressive disclosure to real reference files, but it is padded with definitional content and the workflow lacks validation checkpoints or concrete executable guidance for the core drafting tasks.

Suggestions

Trim definitional padding (agency mission statements and the restated overview paragraph) since Claude already knows these agencies.

Add explicit validation checkpoints to the workflow, e.g. 'Verify page limits and required sections per agency before finalizing' with a concrete check.

Provide at least one worked, copy-paste-ready example for a core task (e.g., a specific-aims or significance-statement template filled in) rather than only activity/output lists.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the overview paragraph, agency mission statements, and restated definitions add padding Claude does not need; it could be tightened without losing clarity.	3 / 5
Actionability	It provides one concrete executable command and real file pointers, but the bulk of the workflow is activity/output lists rather than copy-paste-ready steps or worked examples for the core tasks.	3 / 5
Workflow Clarity	The five-phase workflow is clearly sequenced with activities and outputs, but there are no validation checkpoints or feedback loops (e.g., verify page limits, compliance checks) for the multi-step drafting process.	3 / 5
Progressive Disclosure	SKILL.md is a well-organized overview pointing one level deep to verified reference and asset files (core_components.md, review_criteria.md, templates), each clearly signaled and easy to navigate.	5 / 5
	Total	14 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive, naming concrete agencies and capabilities, but it omits an explicit 'when to use' trigger clause, which the rubric penalizes by capping completeness at 3. Adding a 'Use when...' sentence would raise the overall score.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when writing or revising research proposals, specific aims, budgets, or broader-impacts statements for these agencies.'

Add natural synonyms users may say, such as 'grant proposals', 'fellowship applications', or 'R01 / NSF grant', to broaden trigger-term coverage.

Keep the third-person voice but consider a brief trigger phrase to make the 'when' as explicit as the 'what'.

Dimension	Reasoning	Score
Specificity	Lists five concrete agencies plus seven specific capabilities (formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, compliance), giving comprehensive coverage of concrete actions.	5 / 5
Completeness	The 'what' is explicit and detailed, but there is no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms like 'research proposals', agency names, 'broader impacts', and 'budget preparation' match what users say, but it omits some common synonyms and the second-person phrasing reduces the natural-trigger feel slightly.	4 / 5
Distinctiveness Conflict Risk	Named federal agencies plus grant-specific concepts (broader impacts, significance statements, innovation narratives) carve a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/research-grants/SKILL.md
Commit: 1e5eeff

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.